|
https://github.com/onnx/onnx-tensorrt/blob/84b5be1d6fc03564f2c0dba85a2ee75bad242c2e/oper
ators.md
?
| Operator | Supported? | Restrictions |
|---|
| Abs | Y | | | Acos | Y | | | Acosh | Y | | | Add | Y | | | And | Y | | | ArgMax | Y | | | ArgMin | Y | | | Asin | Y | | | Asinh | Y | | | Atan | Y | | | Atanh | Y | | | AveragePool | Y | 2D or 3D Pooling only | | BatchNormalization | Y | | | BitShift | N | | | Cast | Y | Cast is only supported for TRT types | | Ceil | Y | | | Clip | Y | min and max clip values must be an initializer | | Compress | N | | | Concat | Y | | | ConcatFromSequence N | | | | Constant | Y | | | ConstantOfShape | Y | | | Conv | Y | 2D or 3D convolutions only | | ConvInteger | N | | | ConvTranspose | Y | 2D or 3D deconvolutions only. Weights must be an initializer | | Cos | Y | | | Cosh | Y | | | CumSum | N | | | DepthToSpace | Y | | | DequantizeLinear | Y | Scales and zero-point value must be initializers | | Det | N | | | Div | Y | | | Dropout | N | | | Elu | Y | | | Equal | Y | | | Erf | Y | | | Exp | Y | | | Expand | Y | | | EyeLike | N | | | Flatten | Y | | | Floor | Y | | | Gather | Y | | | GatherElements | N | | | GatherND | N | | | Gemm | Y | | | GlobalAveragePool | Y | | | GlobalLpPool | N | | | GlobalMaxPool | Y | | | Greater | Y | | | GRU | Y | | | HardSigmoid | Y | | | Hardmax | N | | | Identity | Y | | | If | N | | | ImageScaler | Y | | | InstanceNormalization | Y | Scales and biases must be an initializer | | IsInf | N | | | IsNaN | N | | | LeakyRelu | Y | | | Less | Y | | | Log | Y | | | LogSoftmax | Y | | | Loop | Y | | | LRN | Y | | | LSTM | Y | | | LpNormalization | N | | | LpPool | N | | | MatMul | Y | | | MatMulInteger | N | | | Max | Y | | | MaxPool | Y | | | MaxRoiPool | N | | | MaxUnpool | N | | | Mean | Y | | | Min | Y | | | Mod | N | | | Mul | Y | | | Multinomial | N | | | Neg | Y | | | NonMaxSuppression | N | | | NonZero | N | | | Not | Y | | | OneHot | N | | | Or | Y | | | Pad | Y | Zero-padding on last 2 dimensions only | | ParametricSoftplus | Y | | | Pow | Y | | | PRelu | Y | | | QLinearConv | N | | | QLinearMatMul | N | | | QuantizeLinear | Y | Scales and zero-point value must be initializers | | RNN | N | | | RandomNormal | N | | | RandomNormalLike | N | | | RandomUniform | Y | | | RandomUniformLike | Y | | | Range | Y | Float inputs are only supported if start, limit and delta inputs are initializers | | Reciprocal | N | | | ReduceL1 | Y | | | ReduceL2 | Y | | | ReduceLogSum | Y | | | ReduceLogSumExp | Y | | | ReduceMax | Y | | | ReduceMean | Y | | | ReduceMin | Y | | | ReduceProd | Y | | | ReduceSum | Y | | | ReduceSumSquare | Y | | | Relu | Y | | | Reshape | Y | | | Resize | Y | Asymmetric coordinate transformation mode only. Nearest or Linear resizing mode only. "floor" mode only for resize_mode attribute. | | ReverseSequence | N | | | RNN | Y | | | RoiAlign | N | | | Round | N | | | ScaledTanh | Y | | | Scan | Y | | | Scatter | N | | | ScatterElements | N | | | ScatterND | N | | | Selu | Y | | | SequenceAt | N | | | SequenceConstruct | N | | | SequenceEmpty | N | | | SequenceErase | N | | | SequenceInsert | N | | | SequenceLength | N | | | Shape | Y | | | Shrink | N | | | Sigmoid | Y | | | Sign | N | | | Sin | Y | | | Sinh | Y | | | Size | Y | | | Slice | Y | Slice axes must be an initializer | | Softmax | Y | | | Softplus | Y | | | Softsign | Y | | | SpaceToDepth | Y | | | Split | Y | | | SplitToSequence | N | | | Sqrt | Y | | | Squeeze | Y | | | StringNormalizer | N | | | Sub | Y | | | Sum | Y | | | Tan | Y | | | Tanh | Y | | | TfIdfVectorizer | N | | | ThresholdedRelu | Y | | | Tile | Y | | | TopK | Y | | | Transpose | Y | | | Unique | N | | | Unsqueeze | Y | | | Upsample | Y | | | Where | Y | | | Xor | N | |
onnx-tensorrt/operators.md at main · onnx/onnx-tensorrt · GitHub
| Operator | Supported | Supported Types | Restrictions |
|---|
| Abs | Y | FP32, FP16, INT32 | | | Acos | Y | FP32, FP16 | | | Acosh | Y | FP32, FP16 | | | Add | Y | FP32, FP16, INT32 | | | And | Y | BOOL | | | ArgMax | Y | FP32, FP16 | | | ArgMin | Y | FP32, FP16 | | | Asin | Y | FP32, FP16 | | | Asinh | Y | FP32, FP16 | | | Atan | Y | FP32, FP16 | | | Atanh | Y | FP32, FP16 | | | AveragePool | Y | FP32, FP16, INT8, INT32 | 2D or 3D Pooling only | | BatchNormalization | Y | FP32, FP16 | | | BitShift | N | | | | Cast | Y | FP32, FP16, INT32, INT8, BOOL | | | Ceil | Y | FP32, FP16 | | | Celu | Y | FP32, FP16 | | | Clip | Y | FP32, FP16, INT8 | | | Compress | N | | | | Concat | Y | FP32, FP16, INT32, INT8, BOOL | | | ConcatFromSequence | N | | | | Constant | Y | FP32, FP16, INT32, INT8, BOOL | | | ConstantOfShape | Y | FP32 | | | Conv | Y | FP32, FP16, INT8 | 2D or 3D convolutions only. Weights W must be an initailizer | | ConvInteger | N | | | | ConvTranspose | Y | FP32, FP16, INT8 | 2D or 3D deconvolutions only. Weights W must be an initializer | | Cos | Y | FP32, FP16 | | | Cosh | Y | FP32, FP16 | | | CumSum | Y | FP32, FP16 | axis must be an initializer | | DepthToSpace | Y | FP32, FP16, INT32 | | | DequantizeLinear | Y | INT8 | x_zero_point must be zero | | Det | N | | | | Div | Y | FP32, FP16, INT32 | | | Dropout | Y | FP32, FP16 | | | DynamicQuantizeLinear | N | | | | Einsum | Y | FP32, FP16 | Ellipsis and diagonal operations are not supported. Broadcasting between inputs is not supported | | Elu | Y | FP32, FP16, INT8 | | | Equal | Y | FP32, FP16, INT32 | | | Erf | Y | FP32, FP16 | | | Exp | Y | FP32, FP16 | | | Expand | Y | FP32, FP16, INT32, BOOL | | | EyeLike | Y | FP32, FP16, INT32, BOOL | | | Flatten | Y | FP32, FP16, INT32, BOOL | | | Floor | Y | FP32, FP16 | | | Gather | Y | FP32, FP16, INT8, INT32 | | | GatherElements | Y | FP32, FP16, INT8, INT32 | | | GatherND | Y | FP32, FP16, INT8, INT32 | | | Gemm | Y | FP32, FP16, INT8 | | | GlobalAveragePool | Y | FP32, FP16, INT8 | | | GlobalLpPool | Y | FP32, FP16, INT8 | | | GlobalMaxPool | Y | FP32, FP16, INT8 | | | Greater | Y | FP32, FP16, INT32 | | | GreaterOrEqual | Y | FP32, FP16, INT32 | | | GRU | Y | FP32, FP16 | For bidirectional GRUs, activation functions must be the same for both the forward and reverse pass | | HardSigmoid | Y | FP32, FP16, INT8 | | | Hardmax | N | | | | Identity | Y | FP32, FP16, INT32, INT8, BOOL | | | If | Y | FP32, FP16, INT32, BOOL | Output tensors of the two conditional branches must have broadcastable shapes, and must have different names | | ImageScaler | Y | FP32, FP16 | | | InstanceNormalization | Y | FP32, FP16 | Scales scale and biases B must be initializers. Input rank must be >=3 & <=5 | | IsInf | N | | | | IsNaN | Y | FP32, FP16, INT32 | | | LeakyRelu | Y | FP32, FP16, INT8 | | | Less | Y | FP32, FP16, INT32 | | | LessOrEqual | Y | FP32, FP16, INT32 | | | Log | Y | FP32, FP16 | | | LogSoftmax | Y | FP32, FP16 | | | Loop | Y | FP32, FP16, INT32, BOOL | | | LRN | Y | FP32, FP16 | | | LSTM | Y | FP32, FP16 | For bidirectional LSTMs, activation functions must be the same for both the forward and reverse pass | | LpNormalization | Y | FP32, FP16 | | | LpPool | Y | FP32, FP16, INT8 | | | MatMul | Y | FP32, FP16 | | | MatMulInteger | N | | | | Max | Y | FP32, FP16, INT32 | | | MaxPool | Y | FP32, FP16, INT8 | 2D or 3D pooling only. Indices output tensor unsupported | | MaxRoiPool | N | | | | MaxUnpool | N | | | | Mean | Y | FP32, FP16, INT32 | | | MeanVarianceNormalization | N | | | | Min | Y | FP32, FP16, INT32 | | | Mod | N | | | | Mul | Y | FP32, FP16, INT32 | | | Multinomial | N | | | | Neg | Y | FP32, FP16, INT32 | | | NegativeLogLikelihoodLoss | N | | | | NonMaxSuppression | Y [EXPERIMENTAL] | FP32, FP16 | Inputs max_output_boxes_per_class, iou_threshold, and score_threshold must be initializers. Output has fixed shape and is padded to [max_output_boxes_per_class, 3]. | | NonZero | N | | | | Not | Y | BOOL | | | OneHot | N | | | | Or | Y | BOOL | | | Pad | Y | FP32, FP16, INT8, INT32 | | | ParametricSoftplus | Y | FP32, FP16, INT8 | | | Pow | Y | FP32, FP16 | | | PRelu | Y | FP32, FP16, INT8 | | | QLinearConv | N | | | | QLinearMatMul | N | | | | QuantizeLinear | Y | FP32, FP16 | y_zero_point must be 0 | | RandomNormal | N | | | | RandomNormalLike | N | | | | RandomUniform | Y | FP32, FP16 | seed value is ignored by TensorRT | | RandomUniformLike | Y | FP32, FP16 | seed value is ignored by TensorRT | | Range | Y | FP32, FP16, INT32 | Floating point inputs are only supported if start, limit, and delta inputs are initializers | | Reciprocal | N | | | | ReduceL1 | Y | FP32, FP16 | | | ReduceL2 | Y | FP32, FP16 | | | ReduceLogSum | Y | FP32, FP16 | | | ReduceLogSumExp | Y | FP32, FP16 | | | ReduceMax | Y | FP32, FP16 | | | ReduceMean | Y | FP32, FP16 | | | ReduceMin | Y | FP32, FP16 | | | ReduceProd | Y | FP32, FP16 | | | ReduceSum | Y | FP32, FP16 | | | ReduceSumSquare | Y | FP32, FP16 | | | Relu | Y | FP32, FP16, INT8 | | | Reshape | Y | FP32, FP16, INT32, INT8, BOOL | | | Resize | Y | FP32, FP16 | Supported resize transformation modes: half_pixel, pytorch_half_pixel, tf_half_pixel_for_nn, asymmetric, and align_corners.
Supported resize modes: nearest, linear.
Supported nearest modes: floor, ceil, round_prefer_floor, round_prefer_ceil | | ReverseSequence | Y | FP32, FP16 | Dynamic input shapes are unsupported | | RNN | Y | FP32, FP16 | For bidirectional RNNs, activation functions must be the same for both the forward and reverse pass | | RoiAlign | N | | | | Round | Y | FP32, FP16, INT8 | | | ScaledTanh | Y | FP32, FP16, INT8 | | | Scan | Y | FP32, FP16 | | | Scatter | Y | FP32, FP16, INT8, INT32 | | | ScatterElements | Y | FP32, FP16, INT8, INT32 | | | ScatterND | Y | FP32, FP16, INT8, INT32 | | | Selu | Y | FP32, FP16, INT8 | | | SequenceAt | N | | | | SequenceConstruct | N | | | | SequenceEmpty | N | | | | SequenceErase | N | | | | SequenceInsert | N | | | | SequenceLength | N | | | | Shape | Y | FP32, FP16, INT32, INT8, BOOL | | | Shrink | N | | | | Sigmoid | Y | FP32, FP16, INT8 | | | Sign | Y | FP32, FP16, INT8, INT32 | | | Sin | Y | FP32, FP16 | | | Sinh | Y | FP32, FP16 | | | Size | Y | FP32, FP16, INT32, INT8, BOOL | | | Slice | Y | FP32, FP16, INT32, INT8, BOOL | axes must be an initializer | | Softmax | Y | FP32, FP16 | | | SoftmaxCrossEntropyLoss | N | | | | Softplus | Y | FP32, FP16, INT8 | | | Softsign | Y | FP32, FP16, INT8 | | | SpaceToDepth | Y | FP32, FP16, INT32 | | | Split | Y | FP32, FP16, INT32, BOOL | | | SplitToSequence | N | | | | Sqrt | Y | FP32, FP16 | | | Squeeze | Y | FP32, FP16, INT32, INT8, BOOL | axes must be an initializer | | StringNormalizer | N | | | | Sub | Y | FP32, FP16, INT32 | | | Sum | Y | FP32, FP16, INT32 | | | Tan | Y | FP32, FP16 | | | Tanh | Y | FP32, FP16, INT8 | | | TfIdfVectorizer | N | | | | ThresholdedRelu | Y | FP32, FP16, INT8 | | | Tile | Y | FP32, FP16, INT32, BOOL | | | TopK | Y | FP32, FP16 | K input must be an initializer | | Transpose | Y | FP32, FP16, INT32, INT8, BOOL | | | Unique | N | | | | Unsqueeze | Y | FP32, FP16, INT32, INT8, BOOL | axes must be a constant tensor | | Upsample | Y | FP32, FP16 | | | Where | Y | FP32, FP16, INT32, BOOL | | | Xor | N | | |
https://github.com/onnx/onnx/blob/main/docs/Operators.md
| Operator | Since version |
|---|
| Abs | 13, 6, 1 | | Acos | 7 | | Acosh | 9 | | Add | 14, 13, 7, 6, 1 | | And | 7, 1 | | ArgMax | 13, 12, 11, 1 | | ArgMin | 13, 12, 11, 1 | | Asin | 7 | | Asinh | 9 | | Atan | 7 | | Atanh | 9 | | AveragePool | 11, 10, 7, 1 | | BatchNormalization | 15, 14, 9, 7, 6, 1 | | BitShift | 11 | | Cast | 13, 9, 6, 1 | | Ceil | 13, 6, 1 | | Clip | 13, 12, 11, 6, 1 | | Compress | 11, 9 | | Concat | 13, 11, 4, 1 | | ConcatFromSequence | 11 | | Constant | 13, 12, 11, 9, 1 | | ConstantOfShape | 9 | | Conv | 11, 1 | | ConvInteger | 10 | | ConvTranspose | 11, 1 | | Cos | 7 | | Cosh | 9 | | CumSum | 14, 11 | | DepthToSpace | 13, 11, 1 | | DequantizeLinear | 13, 10 | | Det | 11 | | Div | 14, 13, 7, 6, 1 | | Dropout | 13, 12, 10, 7, 6, 1 | | Einsum | 12 | | Elu | 6, 1 | | Equal | 13, 11, 7, 1 | | Erf | 13, 9 | | Exp | 13, 6, 1 | | Expand | 13, 8 | | EyeLike | 9 | | Flatten | 13, 11, 9, 1 | | Floor | 13, 6, 1 | | GRU | 14, 7, 3, 1 | | Gather | 13, 11, 1 | | GatherElements | 13, 11 | | GatherND | 13, 12, 11 | | Gemm | 13, 11, 9, 7, 6, 1 | | GlobalAveragePool | 1 | | GlobalLpPool | 2, 1 | | GlobalMaxPool | 1 | | Greater | 13, 9, 7, 1 | | GridSample | 16 | | HardSigmoid | 6, 1 | | Hardmax | 13, 11, 1 | | Identity | 16, 14, 13, 1 | | If | 16, 13, 11, 1 | | InstanceNormalization | 6, 1 | | IsInf | 10 | | IsNaN | 13, 9 | | LRN | 13, 1 | | LSTM | 14, 7, 1 | | LeakyRelu | 16, 6, 1 | | Less | 13, 9, 7, 1 | | Log | 13, 6, 1 | | Loop | 16, 13, 11, 1 | | LpNormalization | 1 | | LpPool | 11, 2, 1 | | MatMul | 13, 9, 1 | | MatMulInteger | 10 | | Max | 13, 12, 8, 6, 1 | | MaxPool | 12, 11, 10, 8, 1 | | MaxRoiPool | 1 | | MaxUnpool | 11, 9 | | Mean | 13, 8, 6, 1 | | Min | 13, 12, 8, 6, 1 | | Mod | 13, 10 | | Mul | 14, 13, 7, 6, 1 | | Multinomial | 7 | | Neg | 13, 6, 1 | | NonMaxSuppression | 11, 10 | | NonZero | 13, 9 | | Not | 1 | | OneHot | 11, 9 | | Optional | 15 | | OptionalGetElement | 15 | | OptionalHasElement | 15 | | Or | 7, 1 | | PRelu | 16, 9, 7, 6, 1 | | Pad | 13, 11, 2, 1 | | Pow | 15, 13, 12, 7, 1 | | QLinearConv | 10 | | QLinearMatMul | 10 | | QuantizeLinear | 13, 10 | | RNN | 14, 7, 1 | | RandomNormal | 1 | | RandomNormalLike | 1 | | RandomUniform | 1 | | RandomUniformLike | 1 | | Reciprocal | 13, 6, 1 | | ReduceL1 | 13, 11, 1 | | ReduceL2 | 13, 11, 1 | | ReduceLogSum | 13, 11, 1 | | ReduceLogSumExp | 13, 11, 1 | | ReduceMax | 13, 12, 11, 1 | | ReduceMean | 13, 11, 1 | | ReduceMin | 13, 12, 11, 1 | | ReduceProd | 13, 11, 1 | | ReduceSum | 13, 11, 1 | | ReduceSumSquare | 13, 11, 1 | | Relu | 14, 13, 6, 1 | | Reshape | 14, 13, 5, 1 | | Resize | 13, 11, 10 | | ReverseSequence | 10 | | RoiAlign | 16, 10 | | Round | 11 | | Scan | 16, 11, 9, 8 | | Scatter (deprecated) | 11, 9 | | ScatterElements | 16, 13, 11 | | ScatterND | 16, 13, 11 | | Selu | 6, 1 | | SequenceAt | 11 | | SequenceConstruct | 11 | | SequenceEmpty | 11 | | SequenceErase | 11 | | SequenceInsert | 11 | | SequenceLength | 11 | | Shape | 15, 13, 1 | | Shrink | 9 | | Sigmoid | 13, 6, 1 | | Sign | 13, 9 | | Sin | 7 | | Sinh | 9 | | Size | 13, 1 | | Slice | 13, 11, 10, 1 | | Softplus | 1 | | Softsign | 1 | | SpaceToDepth | 13, 1 | | Split | 13, 11, 2, 1 | | SplitToSequence | 11 | | Sqrt | 13, 6, 1 | | Squeeze | 13, 11, 1 | | StringNormalizer | 10 | | Sub | 14, 13, 7, 6, 1 | | Sum | 13, 8, 6, 1 | | Tan | 7 | | Tanh | 13, 6, 1 | | TfIdfVectorizer | 9 | | ThresholdedRelu | 10 | | Tile | 13, 6, 1 | | TopK | 11, 10, 1 | | Transpose | 13, 1 | | Trilu | 14 | | Unique | 11 | | Unsqueeze | 13, 11, 1 | | Upsample (deprecated) | 10, 9, 7 | | Where | 16, 9 | | Xor | 7, 1 | | Function | Since version | | Bernoulli | 15 | | CastLike | 15 | | Celu | 12 | | DynamicQuantizeLinear | 11 | | GreaterOrEqual | 16, 12 | | HardSwish | 14 | | LessOrEqual | 16, 12 | | LogSoftmax | 13, 11, 1 | | MeanVarianceNormalization | 13, 9 | | NegativeLogLikelihoodLoss | 13, 12 | | Range | 11 | | Softmax | 13, 11, 1 | | SoftmaxCrossEntropyLoss | 13, 12 |
|